FPGA Based Object Tracking System

This Paper presents an object tracking system based on FPGA using canny edge detection Algorithm. The system consists of canny edge detection algorithm implemented on FPGA kit to identify edges of real time object. Also a tracking and reorganization of object is done by Smartphone camera. Canny edge detection algorithm is key stage in image processing and object recognizing application. The field programmable gate array contains logic componants that can be programmed to perform complex mathematical functions making them highly suitable for the implementation of matrix algorithm. Individual frames acquired from the target video are fed into the FPGA. These are then subject to segmentation, threasholding, filtering stages. Following these the object is tracked by comparing the background frame and the processed updated frame containing the new location of the target. The result of the FPGA implementation in tracking a moving object were found to be correct and suitable for object tracking.

I. Introduction

Now a day's world most sensing applications needs some form of digital signal processing which thus implemented primarily on serial processors. While the required output is achievable, it can be beneficial to take advantage of the parallel processing, low cost, and low power consumption offered by FPGAs (Spartan 3E). The image of object which is to be track or recognized is captured by the Smartphone and the image is fed to the FPGA where edge detection is performed using canny algorithm and object is tracked using SIFT algorithm based on the various parameter like gray scale conversion, thresolding, noise filtering. Object tracking is the process of locating a moving object in time using a Smartphone camera. The algorithm analyses the video frames and outputs the location of moving targets within the video frame.